swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0062
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.84 | 4 | 0.5153 |
| No log | 1.89 | 9 | 0.1425 |
| 0.4963 | 2.95 | 14 | 0.0326 |
| 0.4963 | 4.0 | 19 | 0.0062 |
| 0.0546 | 4.84 | 23 | 0.1113 |
| 0.0546 | 5.89 | 28 | 0.0194 |
| 0.0216 | 6.95 | 33 | 0.0069 |
| 0.0216 | 8.0 | 38 | 0.0099 |
| 0.0203 | 8.42 | 40 | 0.0126 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2